PURPOSE: We developed predictive models using different programming languages and different computing platforms for machine learning (ML) and deep learning (DL) that classify clinical diagnoses in patients with epiphora. We evaluated the diagnostic performance of these models.METHODS: Between January 2016 and September 2017, 250 patients with epiphora who underwent dacryocystography (DCG) and lacrimal scintigraphy (LS) were included in the study. We developed five different predictive models using ML tools, Python-based TensorFlow, R, and Microsoft Azure Machine Learning Studio (MAMLS). A total of 27 clinical characteristics and parameters including variables related to epiphora (VE) and variables related to dacryocystography (VDCG) were used as input data. Apart from this, we developed two predictive convolutional neural network (CNN) models for diagnosing LS images. We conducted this study using supervised learning.RESULTS: Among 500 eyes of 250 patients, 59 eyes had anatomical obstruction, 338 eyes had functional obstruction, and the remaining 103 eyes were normal. For the data set that excluded VE and VDCG, the test accuracies in Python-based TensorFlow, R, multiclass logistic regression in MAMLS, multiclass neural network in MAMLS, and nuclear medicine physician were 81.70%, 80.60%, 81.70%, 73.10%, and 80.60%, respectively. The test accuracies of CNN models in three-class classification diagnosis and binary classification diagnosis were 72.00% and 77.42%, respectively.CONCLUSIONS: ML-based predictive models using different programming languages and different computing platforms were useful for classifying clinical diagnoses in patients with epiphora and were similar to a clinician's diagnostic ability.
Classification ; Dataset ; Diagnosis ; Humans ; Lacrimal Apparatus Diseases ; Learning ; Logistic Models ; Machine Learning ; Nuclear Medicine ; Programming Languages ; Radionuclide Imaging

BACKGROUND: Complete blood count (CBC) results play an important role in peripheral blood smear (PBS) examinations. Many descriptions in PBS reports may simply be translated from CBC parameters. We developed a computer program that automatically generates a PBS draft report based on CBC parameters and age- and sex-matched reference ranges. METHODS: The Java programming language was used to develop a computer program that supports a graphical user interface. Four hematology analyzers from three different laboratories were tested: Sysmex XE-5000 (Sysmex, Kobe, Japan), Sysmex XN-9000 (Sysmex), DxH800 (Beckman Coulter, Brea, CA, USA), and ADVIA 2120i (Siemens Healthcare Diagnostics, Eschborn, Germany). Input data files containing 862 CBC results were generated from hematology analyzers, middlewares, or laboratory information systems. The draft reports were compared with the content of input data files. RESULTS: We developed a computer program that reads CBC results from a data file and automatically writes a draft PBS report. Age- and sex-matched reference ranges can be automatically applied. After examining PBS, users can modify the draft report based on microscopic findings. Recommendations such as suggestions for further evaluations are also provided based on morphological findings, and they can be modified by users. The program was compatible with all four hematology analyzers tested. CONCLUSIONS: Our program is expected to reduce the time required to manually incorporate CBC results into PBS reports. Systematic inclusion of CBC results could help improve the reliability and sensitivity of PBS examinations.
Blood Cell Count* ; Clinical Laboratory Information Systems ; Delivery of Health Care ; Hematology ; Indonesia ; Information Storage and Retrieval ; Programming Languages ; Reference Values

High-throughput transcriptome sequencing, also known as RNA sequencing (RNA-Seq), is a standard technology for measuring gene expression with unprecedented accuracy. Numerous bioconductor packages have been developed for the statistical analysis of RNA-Seq data. However, these tools focus on specific aspects of the data analysis pipeline, and are difficult to appropriately integrate with one another due to their disparate data structures and processing methods. They also lack visualization methods to confirm the integrity of the data and the process. In this paper, we propose an R-based RNA-Seq analysis pipeline called TRAPR, an integrated tool that facilitates the statistical analysis and visualization of RNA-Seq expression data. TRAPR provides various functions for data management, the filtering of low-quality data, normalization, transformation, statistical analysis, data visualization, and result visualization that allow researchers to build customized analysis pipelines.
Base Sequence ; Gene Expression ; Gene Expression Profiling ; Molecular Sequence Data ; Programming Languages ; Sequence Analysis, RNA ; Statistics as Topic ; Transcriptome

To realize the real-time transmission of temperature data and display using the platform of intelligent mobile phone and bluetooth. Application of Arduino Uno R3 in temperature data acquisition of digital temperature sensor DS18B20 acquisition, through the HC-05 bluetooth transmits the data to the intelligent smart phone Android system, realizes transmission of temperature data. Using Java language to write applications program under Android development environment, can achieve real-time temperature data display, storage and drawing temperature fluctuations drawn graphics. Temperature sensor is experimentally tested to meet the body temperature measurement precision and accuracy. This paper can provide a reference for other smart phone mobile medical product development.
Body Temperature ; Cell Phone ; Humans ; Programming Languages ; Software ; Wireless Technology

BACKGROUND: The majority of patients undergoing stem cell transplantation (SCT) require a blood transfusion until the complete engraftment. Because blood transfusion rules for patients with ABO-incompatible SCT are complicated, we developed an ABO-incompatible transfusion management system (ABO-ITMS) for accurate blood transfusion and improved manageability. METHODS: A committee composed of medical doctors, technicians, and a programmer developed ABO-ITMS during the eight months from July 2013 to February 2014. The program has been linked with other databases, including clinical and laboratory databases and resulted in a new subsystem of the health information system. Server computer's operating system was Window Server 2008, and the database manager program was Oracle 11g. Programming language was ASP.Net (VBScript, C #), and the server and client computer were used to connect to the web server using a web browser. RESULTS: ABO-ITMS was designed to follow three main steps by hematologic oncology clinic, laboratory physician, and blood bank. In the first step, a hematologic-oncology clinic doctor inputs SCT recipients' data and appropriate ABO group for each phase of post-transplantation. Laboratory physician enters the isoagglutinin titer and ABO group at the second step. Finally, blood bank workers enter the results of type, screening, and antibody identification. The patient's SCT information and the previous immunohematologic test results are shown on the screen. CONCLUSION: ABO-ITMS can replace the existing complicated system and workflow. ABO-ITMS will contribute to reducing medical error and improving quality of SCT recipient care.
Blood Banks ; Blood Transfusion* ; Health Information Systems ; Humans ; Mass Screening ; Medical Errors ; Programming Languages ; Stem Cell Transplantation* ; Web Browser

In order to realize tumor disease information sharing and unified management, we utilized grid technology to make the data and software resources which distributed in various medical institutions for effective integration so that we could make the heterogeneous resources consistent and interoperable in both semantics and syntax aspects. This article describes the tumor grid framework, the type of the service being packaged in Web Service Description Language (WSDL) and extensible markup language schemas definition (XSD), the client use the serialized document to operate the distributed resources. The service objects could be built by Unified Modeling Language (UML) as middle ware to create application programming interface. All of the grid resources are registered in the index and released in the form of Web Services based on Web Services Resource Framework (WSRF). Using the system we can build a multi-center, large sample and networking tumor disease resource sharing framework to improve the level of development in medical scientific research institutions and the patient's quality of life.
Databases, Factual ; Humans ; Information Storage and Retrieval ; Internet ; Medical Informatics ; methods ; Neoplasms ; Programming Languages ; Systems Integration

A design scheme of a tele-screening system for diabetic retinopathy (DR) has been proposed, especially the communication subsystem. The scheme uses serial communication module consisting of ARM 7 microcontroller and relays to connect remote computer and fundus camera, and also uses C++ programming language based on MFC to design the communication software consisting of therapy and diagnostic information module, video/audio surveillance module and fundus camera control module. The scheme possesses universal property in some remote medical treatment systems which are similar to the system.
Computers ; Diabetic Retinopathy ; diagnosis ; Humans ; Programming Languages ; Telemedicine ; instrumentation

BACKGROUND AND OBJECTIVES: It takes considerable time and effort to make an operation record for the chronic otitis media. Also there are risks of incorrectness or omission of data. We developed an automatic operation recording system in order to reduce the burden of the resident keeping the record and to give completeness to the operation data. SUBJECTS AND METHOD: The model-view-controller (MVC) pattern isolates the domain logic (controller) from the user interface (data model-view), permitting independent development. We used the MVC pattern to design the program it since it matched with the feature of the operation recording system. RESULTS: We implemented this system using the Python programming language, which is composed of 98 fields and 4 different types of widgets linked to those fields. The outputs of the 4 views can be easily copied and pasted to the word processor and the electronic medical recorder. In the pilot test, this system reduced significant amount of time and effort needed for operation recording. CONCLUSION: The automatic operation recording system reduces the resident's works and the operation data loss. Furthermore, it could be applied to other types of operation records.
Boidae ; Coat Protein Complex I ; Electronic Health Records ; Logic ; Otitis ; Otitis Media ; Programming Languages

Enhanced extracorporeal counterpulsation (EECP) information consists of both text and hemodynamic waveform data. At present EECP text information has been successfully managed through Web browser, while the management and sharing of hemodynamic waveform data through Internet has not been solved yet. In order to manage EECP information completely, based on the in-depth analysis of EECP hemodynamic waveform file of digital imaging and communications in medicine (DICOM) format and its disadvantages in Internet sharing, we proposed the use of the extensible markup language (XML), which is currently the Internet popular data exchange standard, as the storage specification for the sharing of EECP waveform data. Then we designed a web-based sharing system of EECP hemodynamic waveform data via ASP. NET 2.0 platform. Meanwhile, we specifically introduced the four main system function modules and their implement methods, including DICOM to XML conversion module, EECP waveform data management module, retrieval and display of EECP waveform module and the security mechanism of the system.
Computer Communication Networks ; standards ; Counterpulsation ; methods ; Heart-Assist Devices ; Hemodynamics ; Humans ; Internet ; Medical Records Systems, Computerized ; standards ; Programming Languages

The development of external counterpulsation (ECP) local area network system and extensible markup language (XML)-based remote ECP medical information system conformable to digital imaging and communications in medicine (DICOM) standard has been improving the digital interchangeablity and sharability of ECP data. However, the therapy process of ECP is a continuous and longtime supervision which builds a mass of waveform data. In order to reduce the storage space and improve the transmission efficiency, the waveform data with the normative format of ECP data files have to be compressed. In this article, we introduced the compression arithmetic of template matching and improved quick fitting of linear approximation distance thresholding (LADT) in combimation with the characters of enhanced external counterpulsation (EECP) waveform signal. The DICOM standard is used as the storage and transmission standard to make our system compatible with hospital information system. According to the rules of transfer syntaxes, we defined private transfer syntax for one-dimensional compressed waveform data and stored EECP data into a DICOM file. Testing result indicates that the compressed and normative data can be correctly transmitted and displayed between EECP workstations in our EECP laboratory.
Computer Communication Networks ; standards ; Counterpulsation ; methods ; Humans ; Information Storage and Retrieval ; Medical Records Systems, Computerized ; standards ; Programming Languages